Гибридная архитектура на основе ResNet-50, Vision Transformers и радиомики для интерпретируемой классификации микрокальцинатов в маммографии
Аннотация
Ранняя и точная классификация микрокальцинатов в маммографических изображениях имеет критическое значение для своевременного выявления рака молочной железы. В данной работе представлен новый гибридный фреймворк, сочетающий ResNet-50 с модулем внимания CBAM, Vision Transformer (ViT) и радиомические признаки. Такой дизайн позволяет объединить преимущества глубоких сверточных сетей для извлечения локальных текстурных характеристик, трансформеров для моделирования глобальных зависимостей и радиомики для повышения интерпретируемости и клинической обоснованности. Эксперименты были проведены на датасете CBIS-DDSM с внешней валидацией на INbreast. Результаты продемонстрировали превосходство предложенного подхода над базовыми моделями по всем метрикам: Accuracy = 97.80%, ROC-AUC = 98.4%, при минимальной ошибке калибровки (ECE = 0.023). Важным преимуществом является интеграция Grad-CAM, обеспечивающая прозрачность процесса классификации и позволяющая визуализировать зоны интереса. Таким образом, предложенный гибридный фреймворк представляет собой надёжный и интерпретируемый инструмент, который может способствовать практическому внедрению систем искусственного интеллекта в клиническую маммографию для поддержки принятия решений.
Литература
1. Aerts H.J.W.L., et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature communications. 2014;5:4006. https://doi.org/10.1038/ncomms5006
2. Ara S., Das A., Dey A. Malignant and Benign Breast Cancer Classification using Machine Learning Algorithms. In: 2021 International Conference on Artificial Intelligence (ICAI). Islamabad, Pakistan: IEEE Press; 2021. p. 97-101. https://doi.org/10.1109/ICAI52203.2021.9445249
3. Araújo T., et al. Classification of breast cancer histology images using Convolutional Neural Networks. PLoS ONE. 2017;12(6):e0177544. https://doi.org/10.1371/journal.pone.0177544
4. Arnold M., et al. Current and future burden of breast cancer: Global statistics for 2020 and 2040. The Breast. 2022;66:15-23. https://doi.org/10.1016/j.breast.2022.08.010
5. Ayana G., et al. Vision-transformer-based transfer learning for mammogram classification. Diagnostics. 2023;13(2):178. https://doi.org/10.3390/diagnostics13020178
6. Barchuk A., Raskina Y., Tursun-Zade R., Craig H., Are C., Gushchin V. Cancer on the Global Stage: Incidence and Cancer-Related Mortality in the Russian Federation. JAMA. ASCO Post. 2022.
7. Bejani M.M., Ghatee M.A systematic review on overfitting control in shallow and deep neural networks. Artificial Intelligence Review. 2021;54:6391-6438. https://doi.org/10.1007/s10462-021-09975-1
8. Camurdan O., et al. Annotation-efficient, patch-based, explainable deep learning using curriculum method for breast cancer detection in screening mammography. Insights into Imaging. 2025;16:60. https://doi.org/10.1186/s13244-025-01922-w
9. Chan H.P., Samala R.K., Hadjiiski L.M., Zhou C. Deep Learning in Medical Image Analysis. In: Lee, G., Fujita, H. (eds) Deep Learning in Medical Image Analysis. Advances in Experimental Medicine and Biology. Vol. 1213. Cham: Springer; 2020. p. 3-21. https://doi.org/10.1007/978-3-030-33128-3_1
10. Cheng J.-Z., et al. Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans. Scientific reports. 2016;6:24454. https://doi.org/10.1038/srep24454
11. Dosovitskiy A., et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929. 2020. https://doi.org/10.48550/arXiv.2010.11929
12. Du H., Feng J., Feng M. Zoom in to where it matters: a hierarchical graph based model for mammogram analysis. arXiv:1912.07517. 2019. https://doi.org/10.48550/arXiv.1912.07517
13. El-Banby G.M., et al. Automated abnormalities detection in mammography using deep learning. Complex and Intelligent Systems. 2024;10:7279-7295. https://doi.org/10.1007/s40747-024-01532-x
14. Hassan N.M., Hamad S., Mahar K. Mammogram breast cancer CAD systems for mass detection and classification: a review. Multimedia Tools and Applications. 2022;81:20043-20075. https://doi.org/10.1007/s11042-022-12332-1
15. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE Press; 2016. p. 770-778. https://doi.org/ 10.1109/CVPR.2016.90
16. Islam W., et al. Improving performance of breast lesion classification using a ResNet50 model optimized with a novel attention mechanism. Tomography. 2022;8(5):2411-2425. https://doi.org/10.3390/tomography8050200
17. Zhenfei W., et al. Hybrid Feature Extraction for Breast Cancer Classification Using the Ensemble Residual VGG16 Deep Learning Model. Current Bioinformatics. 2025;20:149-163. https://doi.org/10.2174/0115748936333380240816053223
18. Kim S., et al. Microcalcifications, mammographic breast density, and risk of breast cancer: a cohort study. Breast Cancer Research. 2022;24:96. https://doi.org/10.1186/s13058-022-01594-0
19. Kumar V., et al. Radiomics: the process and the challenges. Magnetic Resonance Imaging. 2012;30(9):1234-1248. https://doi.org/10.1016/j.mri.2012.06.010
20. Lee R.S., et al. A curated mammography data set for use in computer-aided detection and diagnosis research. Scientific data. 2017;4:170177. https://doi.org/10.1038/sdata.2017.177
21. Li R., et al. Breast cancer X-ray image staging : based on efficient net with multi-scale fusion and cbam attention. Journal of Physics: Conference Series. 2021;2082 (2021):012006. https://doi.org/10.1088/1742-6596/2082/1/012006
22. Logullo A.F., et al. Breast microcalcifications: Past, present and future. Molecular and clinical oncology. 2022;16(4):81. https://doi.org/10.3892/mco.2022.2514
23. Mahanani M.R., et al. Comparison of female breast cancer between Russia and Germany: A population-based study on time trends and stage at diagnosis. Cancer Epidemiology. 2022;80:102214. https://doi.org/10.1016/j.canep.2022.102214
24. Mahmood T., et al. An Automatic Detection and Localization of Mammographic Microcalcifications ROI with Multi-Scale Features Using the Radiomics Analysis Approach. Cancers. 2021;13(23):5916. https://doi.org/10.3390/cancers13235916
25. Moghbel M., Mashohor S. A review of computer assisted detection/diagnosis (CAD) in breast thermography for breast cancer detection. Artificial Intelligence Review. 2013;39:305-313. https://doi.org/10.1007/s10462-011-9274-2
26. Moreira I.C., et al. Inbreast: toward a full-field digital mammographic database. Academic radiology. 2012;19(2):236-248. https://doi.org/10.1016/j.acra.2011.09.014
27. Murty P.S.R.C., et al. Integrative hybrid deep learning for enhanced breast cancer diagnosis: leveraging the Wisconsin Breast Cancer Database and the CBIS-DDSM dataset. Scientific Reports. 2024;14:26287. https://doi.org/10.1038/s41598-024-74305-8
28. Nalawade Y.V Evaluation of breast calcifications. Indian Journal of radiology and imaging. 2009;19(4):282-286. https://doi.org/10.4103/0971-3026.57208
29. O’Grady S., Morgan M.P. Microcalcifications in breast cancer: From pathophysiology to diagnosis and prognosis. Biochimica et Biophysica Acta – Reviews on Cancer. 2018;1869(2):310-320. https://doi.org/10.1016/j.bbcan.2018.04.006
30. Sajid U., et al. Breast cancer classification using deep learned features boosted with handcrafted features. Biomedical Signal Processing and Control. 2023;86(C):105353. https://doi.org/10.1016/j.bspc.2023.105353
31. Sengodan N. EfficientNet with Hybrid Attention Mechanisms for Enhanced Breast Histopathology Classification : A Comprehensive Approach. arXiv:2410.22392v2. 2024.
32. Shah S.M., et al. Artificial intelligence for breast cancer analysis: Trends & directions. Computers in Biology and Medicine. 2022;142:105221. https://doi.org/10.1016/j.compbiomed.2022.105221
33. Sharma S., Singh Y., Choudhury T. Advanced deep learning architectures for enhanced mammography classification : a comparative study of CNNs and ViT. Discover Artificial Intelligence. 2025;5:187. https://doi.org/10.1007/s44163-025-00426-2
34. Singh L., Alam A. An efficient hybrid methodology for an early detection of breast cancer in digital mammograms. Journal of Ambient Intelligence and Humanized Computing. 2024;15:337-360. https://doi.org/10.1007/s12652-022-03895-w
35. Teoh J.R., et al. Enhancing early breast cancer diagnosis through automated microcalcification detection using an optimized ensemble deep learning framework. PeerJ Computer Science. 2024;10:e2082. https://doi.org/10.7717/peerj-cs.2082
36. Le Thi H.A., Nguyen V.V., Ouchani S. Gene Selection for Cancer Classification Using DCA. In: Tang C., Ling C.X., Zhou X., Cercone N.J., Li X. (eds.) Advanced Data Mining and Applications. ADMA 2008. Lecture Notes in Computer Science. Vol. 5139. Berlin, Heidelberg: Springer; 2008. p. 62-72. https://doi.org/10.1007/978-3-540-88192-6_8
37. Tot T., et al. The clinical value of detecting microcalcifications on a mammogram. Seminars in Cancer Biology. 2021;72:165-174. https://doi.org/10.1016/j.semcancer.2019.10.024
38. Woo S., et al. CBAM: Convolutional Block Attention Module. In: Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part VII. Lecture Notes in Computer Science. Vol. 11211. Cham: Springer; 2018. p. 3-19. https://doi.org/10.1007/978-3-030-01234-2_1
39. Yang Y., et al. Microcalcification-based tumor malignancy evaluation in fresh breast biopsies with hyperspectral stimulated Raman scattering. Analytical Chemistry. 2021;93(15):6223-6231. https://doi.org/10.1021/acs.analchem.1c00522
40. Yu L., et al. Detection and diagnosis of automated breast ultrasound in patients with BI-RADS category 4 microcalcifications : a retrospective study. BMC Medical Imaging. 2024;24:126. https://doi.org/10.1186/s12880-024-01287-4
41. Zakharova N.A., Duffy S.W., Mackay J., Kotlyarov E.V. The introduction of a breast cancer screening programme in a region with a population at medium-risk for breast cancer: Khanty-Mansiysky autonomous Okrug-Ugra (Russian Federation). Ecancer. 2011;5:195. https://doi.org/10.3332/ecancer.2011.195
42. Zhang Y., et al. Journal of the National Cancer Center Global burden of female breast cancer: new estimates in 2022, temporal trend and future projections up to 2050 based on the latest release from GLOBOCAN 2025. Journal of the National Cancer Center. 2025;5(3):287-296. https://doi.org/10.1016/j.jncc.2025.02.002
43. Zheng T., et al. Deep learning-enabled fully automated pipeline system for segmentation and classification of single-mass breast lesions using contrast-enhanced mammography: a prospective, multicentre study. EClinicalMedicine. 2023;58:101913. https://doi.org/10.1016/j.eclinm.2023.101913
44. Shakhzadova A.O., Starinsky V.V., Lisichnikova I.V. Cancer care to the population of Russia in 2022. Siberian journal of oncology. 2023;22(5):5-13. (In Russ., abstract in Eng.) https://doi.org/10.21294/1814-4861-2023-22-5-5-13
2. Ara S., Das A., Dey A. Malignant and Benign Breast Cancer Classification using Machine Learning Algorithms. In: 2021 International Conference on Artificial Intelligence (ICAI). Islamabad, Pakistan: IEEE Press; 2021. p. 97-101. https://doi.org/10.1109/ICAI52203.2021.9445249
3. Araújo T., et al. Classification of breast cancer histology images using Convolutional Neural Networks. PLoS ONE. 2017;12(6):e0177544. https://doi.org/10.1371/journal.pone.0177544
4. Arnold M., et al. Current and future burden of breast cancer: Global statistics for 2020 and 2040. The Breast. 2022;66:15-23. https://doi.org/10.1016/j.breast.2022.08.010
5. Ayana G., et al. Vision-transformer-based transfer learning for mammogram classification. Diagnostics. 2023;13(2):178. https://doi.org/10.3390/diagnostics13020178
6. Barchuk A., Raskina Y., Tursun-Zade R., Craig H., Are C., Gushchin V. Cancer on the Global Stage: Incidence and Cancer-Related Mortality in the Russian Federation. JAMA. ASCO Post. 2022.
7. Bejani M.M., Ghatee M.A systematic review on overfitting control in shallow and deep neural networks. Artificial Intelligence Review. 2021;54:6391-6438. https://doi.org/10.1007/s10462-021-09975-1
8. Camurdan O., et al. Annotation-efficient, patch-based, explainable deep learning using curriculum method for breast cancer detection in screening mammography. Insights into Imaging. 2025;16:60. https://doi.org/10.1186/s13244-025-01922-w
9. Chan H.P., Samala R.K., Hadjiiski L.M., Zhou C. Deep Learning in Medical Image Analysis. In: Lee, G., Fujita, H. (eds) Deep Learning in Medical Image Analysis. Advances in Experimental Medicine and Biology. Vol. 1213. Cham: Springer; 2020. p. 3-21. https://doi.org/10.1007/978-3-030-33128-3_1
10. Cheng J.-Z., et al. Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans. Scientific reports. 2016;6:24454. https://doi.org/10.1038/srep24454
11. Dosovitskiy A., et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929. 2020. https://doi.org/10.48550/arXiv.2010.11929
12. Du H., Feng J., Feng M. Zoom in to where it matters: a hierarchical graph based model for mammogram analysis. arXiv:1912.07517. 2019. https://doi.org/10.48550/arXiv.1912.07517
13. El-Banby G.M., et al. Automated abnormalities detection in mammography using deep learning. Complex and Intelligent Systems. 2024;10:7279-7295. https://doi.org/10.1007/s40747-024-01532-x
14. Hassan N.M., Hamad S., Mahar K. Mammogram breast cancer CAD systems for mass detection and classification: a review. Multimedia Tools and Applications. 2022;81:20043-20075. https://doi.org/10.1007/s11042-022-12332-1
15. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE Press; 2016. p. 770-778. https://doi.org/ 10.1109/CVPR.2016.90
16. Islam W., et al. Improving performance of breast lesion classification using a ResNet50 model optimized with a novel attention mechanism. Tomography. 2022;8(5):2411-2425. https://doi.org/10.3390/tomography8050200
17. Zhenfei W., et al. Hybrid Feature Extraction for Breast Cancer Classification Using the Ensemble Residual VGG16 Deep Learning Model. Current Bioinformatics. 2025;20:149-163. https://doi.org/10.2174/0115748936333380240816053223
18. Kim S., et al. Microcalcifications, mammographic breast density, and risk of breast cancer: a cohort study. Breast Cancer Research. 2022;24:96. https://doi.org/10.1186/s13058-022-01594-0
19. Kumar V., et al. Radiomics: the process and the challenges. Magnetic Resonance Imaging. 2012;30(9):1234-1248. https://doi.org/10.1016/j.mri.2012.06.010
20. Lee R.S., et al. A curated mammography data set for use in computer-aided detection and diagnosis research. Scientific data. 2017;4:170177. https://doi.org/10.1038/sdata.2017.177
21. Li R., et al. Breast cancer X-ray image staging : based on efficient net with multi-scale fusion and cbam attention. Journal of Physics: Conference Series. 2021;2082 (2021):012006. https://doi.org/10.1088/1742-6596/2082/1/012006
22. Logullo A.F., et al. Breast microcalcifications: Past, present and future. Molecular and clinical oncology. 2022;16(4):81. https://doi.org/10.3892/mco.2022.2514
23. Mahanani M.R., et al. Comparison of female breast cancer between Russia and Germany: A population-based study on time trends and stage at diagnosis. Cancer Epidemiology. 2022;80:102214. https://doi.org/10.1016/j.canep.2022.102214
24. Mahmood T., et al. An Automatic Detection and Localization of Mammographic Microcalcifications ROI with Multi-Scale Features Using the Radiomics Analysis Approach. Cancers. 2021;13(23):5916. https://doi.org/10.3390/cancers13235916
25. Moghbel M., Mashohor S. A review of computer assisted detection/diagnosis (CAD) in breast thermography for breast cancer detection. Artificial Intelligence Review. 2013;39:305-313. https://doi.org/10.1007/s10462-011-9274-2
26. Moreira I.C., et al. Inbreast: toward a full-field digital mammographic database. Academic radiology. 2012;19(2):236-248. https://doi.org/10.1016/j.acra.2011.09.014
27. Murty P.S.R.C., et al. Integrative hybrid deep learning for enhanced breast cancer diagnosis: leveraging the Wisconsin Breast Cancer Database and the CBIS-DDSM dataset. Scientific Reports. 2024;14:26287. https://doi.org/10.1038/s41598-024-74305-8
28. Nalawade Y.V Evaluation of breast calcifications. Indian Journal of radiology and imaging. 2009;19(4):282-286. https://doi.org/10.4103/0971-3026.57208
29. O’Grady S., Morgan M.P. Microcalcifications in breast cancer: From pathophysiology to diagnosis and prognosis. Biochimica et Biophysica Acta – Reviews on Cancer. 2018;1869(2):310-320. https://doi.org/10.1016/j.bbcan.2018.04.006
30. Sajid U., et al. Breast cancer classification using deep learned features boosted with handcrafted features. Biomedical Signal Processing and Control. 2023;86(C):105353. https://doi.org/10.1016/j.bspc.2023.105353
31. Sengodan N. EfficientNet with Hybrid Attention Mechanisms for Enhanced Breast Histopathology Classification : A Comprehensive Approach. arXiv:2410.22392v2. 2024.
32. Shah S.M., et al. Artificial intelligence for breast cancer analysis: Trends & directions. Computers in Biology and Medicine. 2022;142:105221. https://doi.org/10.1016/j.compbiomed.2022.105221
33. Sharma S., Singh Y., Choudhury T. Advanced deep learning architectures for enhanced mammography classification : a comparative study of CNNs and ViT. Discover Artificial Intelligence. 2025;5:187. https://doi.org/10.1007/s44163-025-00426-2
34. Singh L., Alam A. An efficient hybrid methodology for an early detection of breast cancer in digital mammograms. Journal of Ambient Intelligence and Humanized Computing. 2024;15:337-360. https://doi.org/10.1007/s12652-022-03895-w
35. Teoh J.R., et al. Enhancing early breast cancer diagnosis through automated microcalcification detection using an optimized ensemble deep learning framework. PeerJ Computer Science. 2024;10:e2082. https://doi.org/10.7717/peerj-cs.2082
36. Le Thi H.A., Nguyen V.V., Ouchani S. Gene Selection for Cancer Classification Using DCA. In: Tang C., Ling C.X., Zhou X., Cercone N.J., Li X. (eds.) Advanced Data Mining and Applications. ADMA 2008. Lecture Notes in Computer Science. Vol. 5139. Berlin, Heidelberg: Springer; 2008. p. 62-72. https://doi.org/10.1007/978-3-540-88192-6_8
37. Tot T., et al. The clinical value of detecting microcalcifications on a mammogram. Seminars in Cancer Biology. 2021;72:165-174. https://doi.org/10.1016/j.semcancer.2019.10.024
38. Woo S., et al. CBAM: Convolutional Block Attention Module. In: Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part VII. Lecture Notes in Computer Science. Vol. 11211. Cham: Springer; 2018. p. 3-19. https://doi.org/10.1007/978-3-030-01234-2_1
39. Yang Y., et al. Microcalcification-based tumor malignancy evaluation in fresh breast biopsies with hyperspectral stimulated Raman scattering. Analytical Chemistry. 2021;93(15):6223-6231. https://doi.org/10.1021/acs.analchem.1c00522
40. Yu L., et al. Detection and diagnosis of automated breast ultrasound in patients with BI-RADS category 4 microcalcifications : a retrospective study. BMC Medical Imaging. 2024;24:126. https://doi.org/10.1186/s12880-024-01287-4
41. Zakharova N.A., Duffy S.W., Mackay J., Kotlyarov E.V. The introduction of a breast cancer screening programme in a region with a population at medium-risk for breast cancer: Khanty-Mansiysky autonomous Okrug-Ugra (Russian Federation). Ecancer. 2011;5:195. https://doi.org/10.3332/ecancer.2011.195
42. Zhang Y., et al. Journal of the National Cancer Center Global burden of female breast cancer: new estimates in 2022, temporal trend and future projections up to 2050 based on the latest release from GLOBOCAN 2025. Journal of the National Cancer Center. 2025;5(3):287-296. https://doi.org/10.1016/j.jncc.2025.02.002
43. Zheng T., et al. Deep learning-enabled fully automated pipeline system for segmentation and classification of single-mass breast lesions using contrast-enhanced mammography: a prospective, multicentre study. EClinicalMedicine. 2023;58:101913. https://doi.org/10.1016/j.eclinm.2023.101913
44. Shakhzadova A.O., Starinsky V.V., Lisichnikova I.V. Cancer care to the population of Russia in 2022. Siberian journal of oncology. 2023;22(5):5-13. (In Russ., abstract in Eng.) https://doi.org/10.21294/1814-4861-2023-22-5-5-13
Опубликована
2025-10-13
Как цитировать
ALSAJER, Hussein; PHILIPPOVICH, Yuri Nikolaevich; BEKETOVA, Tatyana Valentinovna.
Гибридная архитектура на основе ResNet-50, Vision Transformers и радиомики для интерпретируемой классификации микрокальцинатов в маммографии.
Современные информационные технологии и ИТ-образование, [S.l.], v. 21, n. 3, p. 476-489, oct. 2025.
ISSN 2411-1473. Доступно на: <http://sitito.cs.msu.ru/index.php/SITITO/article/view/1250>. Дата доступа: 07 aug. 2026
doi: https://doi.org/10.25559/SITITO.021.202503.476-489.
Раздел
Исследования и разработки в области новых ИТ и их приложений
Это произведение доступно по лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.
Редакционная политика журнала основывается на традиционных этических принципах российской научной периодики и строится с учетом этических норм работы редакторов и издателей, закрепленных в Кодексе поведения и руководящих принципах наилучшей практики для редактора журнала (Code of Conduct and Best Practice Guidelines for Journal Editors) и Кодексе поведения для издателя журнала (Code of Conduct for Journal Publishers), разработанных Комитетом по публикационной этике - Committee on Publication Ethics (COPE). В процессе издательской деятельности редколлегия журнала руководствуется международными правилами охраны авторского права, нормами действующего законодательства РФ, международными издательскими стандартами и обязательной ссылке на первоисточник.
Журнал позволяет авторам сохранять авторское право без ограничений. Журнал позволяет авторам сохранить права на публикацию без ограничений.
Издательская политика в области авторского права и архивирования определяются «зеленым цветом» в базе данных SHERPA/RoMEO.
Все статьи распространяются на условиях лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная, которая позволяет другим использовать, распространять, дополнять эту работу с обязательной ссылкой на оригинальную работу и публикацию в этом журналe.
